ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-12 01:10:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

reimplement threadwise copy

Browse Source
This commit is contained in:
Chao Liu
2019-08-06 17:41:58 -05:00
parent adc1008836
commit fdcfae3a62
10 changed files with 223 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
driver/include/device_convolution_implicit_gemm_v4r4_nchw_kcyx_nkhw.hpp
View File

@@ -132,7 +132,7 @@ void device_convolution_implicit_gemm_v4r4_nchw_kcyx_nkhw(InDesc,
printf("%s: BlockSize %u, GridSize %u \n", __func__, BlockSize, GridSize);
constexpr auto gridwise_conv =
#if 1
#if 0
GridwiseConvolutionImplicitGemm_v4r4_nchw_kcyx_nkhw
#else
GridwiseConvolutionImplicitGemm_v4r4_nchw_kcyx_nkhw_lds_double_buffer